Permanent Link Feedback

ORTHOGONAL RANK-ONE MATRIX PURSUIT FOR LOW RANK MATRIX COMPLETION


Abstract In this paper, we propose an efficient and scalable low rank matrix completion algorithm. The key idea is to extend the orthogonal matching pursuit method from the vector case to the matrix case. We further propose an economic version of our algorithm by introducing a novel weight updating rule to reduce the time and storage complexity. Both versions are computationally inexpensive for each matrix pursuit iteration and find satisfactory results in a few iterations. Another advantage of our proposed algorithm is that it has only one tunable parameter, which is the rank. It is easy to understand and to use by the user. This becomes especially important in large-scale learning problems. In addition, we rigorously show that both versions achiev... (more)
Created Date 2014-11-30
Contributor Wang, Zheng (Author) / Lai, Ming-Jun (Author) / Lu, Zhaosong (Author) / Fan, Wei (Author) / Davulcu, Hasan (ASU author) / Ye, Jieping (Author) / Arizona State University. School of Computing, Informatics and Decision Systems Engineering
Series SIAM JOURNAL ON SCIENTIFIC COMPUTING
Type Text
Extent 27 pages
Language English
Identifier DOI: 10.1137/130934271 / ISSN: 1095-7197 / ISSN: 1064-8275
Rights All Rights Reserved
Citation Wang, Zheng, Lai, Ming-Jun, Lu, Zhaosong, Fan, Wei, Davulcu, Hasan, & Ye, Jieping (2015). ORTHOGONAL RANK-ONE MATRIX PURSUIT FOR LOW RANK MATRIX COMPLETION. SIAM JOURNAL ON SCIENTIFIC COMPUTING, 37(1). http://dx.doi.org/10.1137/130934271
Note Link to published article.
Collaborating Institutions ASU Libraries
Additional Formats MODS / OAI Dublin Core / RIS


  ORTHOGONAL RANK-ONE MATRIX PURSUIT FOR LOW RANK MATRIX COMPLETION
2.4 MB application/pdf